© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220319
    Prev
    Next
    INDEX
    Explanations

    test case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     प्रा
    0.52
     NGOs
    0.51
     maggiori
    0.50
     escola
    0.50
    Depois
    0.50
    quête
    0.50
    chap
    0.49
     ג
    0.49
    ofo
    0.48
     மண
    0.47
    POSITIVE LOGITS
     was
    0.44
     sees
    0.41
     hauled
    0.41
    屍
    0.40
     blinked
    0.39
    endium
    0.39
     washed
    0.38
     attacked
    0.38
     reacts
    0.38
    ercase
    0.37
    Activations Density 0.000%

    No Known Activations